EP2439641B1 - Server control program, control server, virtual server distribution method - Google Patents
Server control program, control server, virtual server distribution method Download PDFInfo
- Publication number
- EP2439641B1 EP2439641B1 EP09845469.7A EP09845469A EP2439641B1 EP 2439641 B1 EP2439641 B1 EP 2439641B1 EP 09845469 A EP09845469 A EP 09845469A EP 2439641 B1 EP2439641 B1 EP 2439641B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- servers
- physical
- server
- virtual
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Not-in-force
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5019—Workload prediction
Definitions
- the present invention relates to a technology of virtual computing that causes plural virtual servers to operate on plural physical servers and more specifically to scheduling in distribution of the virtual servers to the physical servers.
- Patent Document 2 discloses a virtual server system and physical server selecting method, wherein the method uses resource information of physical servers and virtual servers, and capacity information of physical servers, to allocate virtual servers to physical servers with spare capacity.
- one aspect of the present invention intends to provide a server control program, a control server, and a virtual server distribution method for efficient distribution in distributing plural virtual servers to plural physical servers in terms of the processing capacity of the physical servers and their power consumption.
- system a network system including a control server according to an embodiment
- this system has a control server 2, a control terminal 3, and a controlled server group 4 connected through a network.
- the control server 2 takes a control so that one or plural virtual servers are distributed for each of the physical servers in the controlled server group 4. At that time, this control intends efficient distribution of the virtual servers in view of the processing capacity of the physical servers and their power consumption.
- the controlled server group 4 includes plural virtual servers (indicated by "V” in FIG. 1 ) and plural physical servers (indicated by "P” in FIG. 1 ), and is a group of servers to be controlled by the control server 2 over the network.
- the physical servers are platforms that cause the virtual servers to operate, and include computer hardware and virtual server control software such as hypervisors.
- the virtual servers are servers realized on the physical servers in the manner of software.
- One or more tasks (applications) run on the virtual servers.
- plural virtual servers carrying out different tasks may be combined and distributed on a physical server, or plural virtual servers carrying out an identical task may be distributed on different physical servers.
- the data of the virtual servers may be stored in a disk device directly connected to the physical servers, or may be stored in a shared disk (such as SAN (Storage Area Network), NFS (Network File System), and iSCSI (Internet Sall Computer System Interface) that is present separately from the physical servers and is connected over a network or by a direct wire connection.
- SAN Storage Area Network
- NFS Network File System
- iSCSI Internet Sall Computer System Interface
- the type of the physical medium of the disk in which the data of the virtual servers is stored is not limited.
- control server 2 can communicate with the controlled server group 4 over a network, the control server 2 is present independently of the controlled server group 4, and controls so as to unify the entire system.
- the control server 2 includes a system control unit 21, a load database (load DB) 22, a server control database (server control DB) 23, a load prediction unit 24, an optimal distribution creation unit 25 (schedule creation unit), a redistribution execution unit 26 (distribution execution unit), a failure monitor unit 27, and a distribution schedule data storage unit 28.
- load DB load database
- server control DB server control database
- load prediction unit a load prediction unit 24
- an optimal distribution creation unit 25 scheduling unit
- redistribution execution unit 26 distributed execution unit
- failure monitor unit 27 a failure monitor unit
- the control terminal 3 is a client including a control information display unit 31.
- the control terminal 3 is connected to the control server 2 directly or over a network.
- FIG. 1 illustrates an example in which the control terminal 3 is connected with the control serer 2 over the network.
- the control information display unit 31 may be implemented in the control terminal 3 or may be implemented in the control server 2.
- FIG. 1 illustrates an example in which the control information display unit 31 is implemented in the control terminal 3.
- the system control unit 21 is mainly composed of microcontrollers, and performs regulation of the entire control server 2, control of each database, and transmission of commands to each unit of the control server 2.
- the control server 2 is composed of plural computers
- the system control unit 21 unifies all of the computers.
- the system control unit 21 performs reception of a request from the control terminal 3, and transmission of data to be displayed in the control terminal 3 in response to the request.
- Previous load data of each virtual server is accumulated in the load database 22.
- the load data includes a load value of each virtual server and information on an operation state (running or stopped) of each virtual server (hereinafter referred to as "operation information").
- the load value included in the load data can be any value as long as the value is an index that can be compared with a processing capacity value described later.
- the load value may be, for example, utilization relating to the resources of a computer such as a CPU, a memory and a disk, an index value synthesizing these resources, or a benchmark value of computing capability necessary to execute a certain number of tasks.
- a route when the load data is accumulated in the load database 22, a method of the accumulation, and a timing of the accumulation are not limited.
- the route when the load data is accumulated in the load database 22 is discussed as an example.
- An agent may be provided on the virtual server side and the agent has functions of measuring the load data and of regularly transmitting the load data to the control server 2, or a manager may be provided to regularly obtain the load data to each virtual server from the control server 2.
- the load data may be transmitted to the control server 2 through a hypervisor operating on the physical server and controlling virtual servers or through an interface of the physical server.
- FIG. 2 is a diagram illustrating an example of a route on which the load data is transmitted in this system.
- the system control unit 21 makes an inquiry at the server control database 23 to obtain information on the virtual servers that are load data obtaining targets (e.g., specific information indicating a location on a network such as a virtual server ID or an IP address). Based on the information of the virtual server, the system control unit 21 makes an inquiry at the hypervisor on the physical server in which the target virtual server is operating through a network.
- the hypervisor has a mechanism to read the load data of the virtual servers and returns the load data of the target virtual server in response to the inquiry from the system control unit 21.
- the system control unit 21 that obtained the load data of the target virtual servers records the load data in a record of corresponding virtual servers ID of the load database 22.
- load data of all virtual servers at a certain point in time can be obtained.
- this data obtaining processing is accumulated in the load database 22.
- FIG. 2(b) illustrates a case in which an agent for transmitting the load data is provided on the virtual servers.
- the agent on the virtual servers transmits the load data directly to the control server 2 without going through the hypervisor.
- the system control unit 21 that received the load data checks the virtual server that transmitted the load data against the server control database 23, and records the virtual server in a record of the virtual server ID of the load database 21.
- FIG. 1 and FIG. 2 explanations are provided under an assumption that the load database 22 and the server control database 23 are present as separate databases. However, these databases may be configured as a single data base (a single table).
- the load value included in the load data recorded periodically in the load database 22 may be an instantaneous value (one sample) , an average value (average of plural samples) , or a total value (a total value of plural samples).
- the number of the samples is not particularly limited.
- the intervals of obtaining the load data are set to at least intervals shorter than the intervals required for load prediction described later.
- the load data recorded in the load database 22 includes not only the load value of each of the virtual servers but also operation information of each of the virtual servers. This operation information is utilized to calculate an accurate prediction value in consideration of stopped periods of the virtual servers in the load prediction described later.
- the system control unit 21 when the system control unit 21 makes an inquiry at the hypervisor, the system control unit 21 obtains the operation information of the target virtual servers together with the load value, and the load data including the load value and the operation information is recorded in the load database 22.
- the virtual server or the hypervisor notifies the system control unit 21 of a change of the operating state of the virtual servers at the time of the virtual servers being started or being stopped. On the basis of this notification, the system control unit 21 records the operation information of the virtual server in the load database 22.
- FIG. 3 illustrates an example of the data structure of the load database 22.
- virtual server IDs (VM1, VM2, ..., VMm) and the load data of the corresponding virtual servers are recorded in the load database 22 in association with plural records (records 1, 2, ..., m).
- the virtual server ID is information to associate the virtual servers on the load database 22 with the virtual servers on the server control database 23.
- the load data includes the load value and the operation information of a virtual server for each point in time of obtaining the load data.
- FIG. 3 illustrates an example of recording actual points in time for each minute as an example of the recording time points of the load data. However, it is not necessary to record the actual points in time. Offsets from the recording start time may be recorded, or texts that can specify the recording time may be recorded.
- the server control database 23 records a list of physical servers and their processing capacity and a list of virtual servers.
- the data of the physical servers and the data of the virtual servers may be present as independent databases as long as the databases are accessible from the control server.
- the processing capacity value of each physical server is an index value indicating the performance relating to processing capacity (or computing capacity) of each physical server, and can be any value as long as it can be compared with the load value described above.
- the processing capacity value may be a value indicating resources of a computer such as a CPU, a memory, or a disk (computing speed and memory capacity), or an index value synthesizing these resources.
- FIG. 4 illustrates an example of content included in tables (physical server table and virtual server table) of the server control database 23.
- a quantity n of physical servers and a quantity m of virtual servers are to be controlled. It should be noted that the number of the virtual servers is larger than the number of the physical servers in general (m>n) .
- Identification (ID) information (e.g. addresses) and the processing capacity values of a quantity n of physical servers corresponding to the record 1 to n are included in the physical server table.
- the physical server table further includes failure information and operation information corresponding to each of the records.
- the failure information of the physical servers is information of whether the physical server is in a normal condition or not (indicating "normal” or "failed”).
- the operation information of physical servers is information relating to the operation state of the physical servers (indicating "running” or “stopped”). The failure information and/or operation information is useful to identify scheduled physical servers when a distribution schedule that is described later is created.
- Identification information, the virtual server ID, and the image data of the virtual servers of the quantity m of physical servers corresponding to the record 1 to m are included in the virtual server table.
- the identification information is information to uniquely identify the physical servers or virtual servers within the control server 2 so as to be accessible to the servers, and computer names and addresses on a network are the examples. In FIG. 4 , addresses are illustrated as an example of the identification information.
- the virtual server ID is used to associate the virtual servers with the records on the load database 22.
- the data structure illustrated in FIG. 4 is only an example, and the structure may have a proper addition of information necessary to control the physical servers and/or virtual servers.
- the load prediction unit 24 operates in accordance with a load prediction algorithm described later, and performs prediction of the future load values (load prediction) in a specific period of time in a specific virtual server based on the load data in the past.
- load prediction the load values and the operation information included in the load data of each of the virtual servers from the load database 22 are references for a certain period to some extent (e.g. one week or one months), or for the entire period of time.
- the predicted load value (second load) is arbitrarily referred to as "load prediction value”. Details of the load prediction algorithm are explained later.
- the optimal distribution creation unit 25 functioning as a schedule creation unit operates in accordance with an optimal distribution creation algorithm described later, and creates an optimal distribution schedule of the virtual servers with respect to the physical servers based on the load value predicted by the load prediction unit 24.
- "optimal distribution” is defined that a total of the load values predicted from plural virtual servers distributed on a physical server is within a range of appropriate proportions (acceptable range) with respect to the processing capacity value of the physical server.
- the upper limit of the acceptable range is provided to give a margin of tolerance for an abrupt increase in a load of the virtual servers, and the lower limit of the acceptable range is provided to reduce power consumption by utilizing the performance of the physical server without any waste and by minimizing the number of physical servers to be operated.
- the optimal distribution creation unit 25 when it creates a distribution schedule, refers respectively to the server control database 23 and the load prediction unit 24.
- the optimal distribution creation algorithm is explained later in more detail.
- the redistribution execution unit 26 performs redistribution of virtual servers in accordance with the distribution schedule created by the optimal distribution creation unit 25.
- the redistribution execution unit 26 includes an interface to issue an instruction of migration.
- An interface provided by virtual server control software such as a hypervisor is mainly used for this interface.
- a method of migration to execute the redistribution is not limited.
- the redistribution execution unit 26 executes offline migration when a virtual server to be migrated is under suspension, but when the virtual server to be migrated is in operation, the redistribution execution unit 26 may stop the operation of the virtual server to execute the offline migration. Moreover, the redistribution execution unit 26 may execute online migration when the virtual server to be migrated is in running.
- the redistribution execution unit 26 includes an interface that can instruct turning on and off of the power of a physical server, and an interface that can instruct migration of the virtual server.
- the redistribution execution unit 26 causes a physical server with zero virtual servers as a result of execution of the redistribution to turn off the power. If a new physical server needs to be activated as a result of execution of the redistribution, the redistribution execution unit 26 activates the physical server. Furthermore, the redistribution execution unit 26, when the physical server fails (when the failure information indicates "failed"), causes the physical server to turn off the power, and activates another physical server.
- the interface used for turning on and off the power may be an interface provided in the physical server itself, control software provided by a vendor of the physical server, a common tool, or a unique implementation. The protocols and the control channels in the interface are not limited.
- a temporarily non-operating physical server may be activated.
- the instruction of turning on/off the power of the physical server and the instruction of the migration of the virtual server from the redistribution execution unit 26 may be made through any protocols.
- the protocols are SNMP (Simple Network Management Protocol), IPMI (Intelligent Platform Management Interface), and SMASH-CLP (System Management Architecture for Server Hardware Command Line Protocol).
- the failure monitor unit 27 monitors the state of each physical server (normal/failed) and, when a failure occurs, rewrites the failure information of the record corresponding to the physical server on the server control database 23 as "failed". When the failed physical server is recovered, the failure monitor unit 27 rewrites the failure information of the record corresponding to the physical server to "normal".
- the distribution schedule data storage unit 28 stores the distribution schedule created by the optimal distribution creation unit 25.
- the redistribution execution unit 26 refers to the distribution schedule stored in the distribution schedule data storage unit 28 to execute redistribution. It should be noted that the distribution schedule is periodically updated.
- the control information display unit 31 displays various information including operation information of the system based on the data provided from the control server 2.
- the information displayed in the control information display unit 31 includes, for example, the following information.
- FIG. 5 is a diagram illustrating a mode of transmitting a request of the control information from the control terminal 3 to the control server 2 and receiving the response.
- the system control unit 21 refers to the load database 22 or the server control database 23, extracts the control information relating to the request, and transmits the control information to the control terminal 3.
- the control terminal 3 causes the control information display unit 31 to display the control information received as the response from the control server 2. As a result, the control information is visible to a system manager operating the control terminal 3, for example.
- each of the virtual servers is a server that operates 24 hours a day or a server having a stopped time period (or operating period) is analyzed. If it is a server having a stopped time period, the stopped time period is predicted.
- a typical virtual server that has a stopped time period is, for example, a virtual server that is used in a method of utilization in which the server does not perform its tasks during weekends or at night.
- the load prediction algorithm can directly use the schedule of the stopped time periods as the prediction value of the stopped time periods.
- a system administrator may register the operation schedule of the virtual server in the server control database 23 in advance.
- the load prediction algorithm predicts (calculates) the stopped time period by analyzing operation information (information in the load database 22; see FIG. 3 ) with respect to a prescribed time block each day (one particular hour) for several weeks. This analysis is conducted by calculating the percentage of time that the virtual server is operating within a particular time block in a day (operation percentage) based on the operation information of the virtual server, for example, and determining that that particular time block is a stopped time period under the condition that the operation percentage is at a prescribed threshold or below.
- the operation information that is the basis of the calculation of the stopped time period may be on a daily, weekly, or monthly basis, or combinations of those.
- the reason to make a distinction between the operating time period and the stopped time period in the load prediction algorithm is that if an average of the load values during the entire time period is calculated, the calculated average value would include the stopped time periods, and this would be smaller than the average of the load values during running and does not match the actual situation.
- FIG. 6 is a diagram illustrating an example of a prediction result (the operation time period or the stopped time period) on an hourly basis within a month.
- FIG. 6 illustrates an example of a matrix having 0 to 23 hours on an hourly basis on a horizontal axis and 0 to 30 days in units of days on a vertical axis, and the time periods represented by gray indicate the stopped time period of the virtual server and the time periods represented by white indicate the operating time period of the virtual server.
- the load prediction algorithm may predict non-business days, business days, and working hours of a particular virtual server based on hourly data illustrated in FIG. 6 .
- one hour of the operating time period and one hour of the stopped time period are referred to as an operating hour and a stopped hour, respectively.
- the load prediction algorithm determines that a day in which operation hours of a virtual server are below a prescribed threshold (e.g., 30%) is a "nonbusiness day" of the virtual server. If this nonbusiness day occurs periodically every seven days, it can be predicted that Saturdays and Sundays are the nonbusiness days of this virtual server, and the virtual server will not operate on Saturdays and Sundays in the future. In contrast, the load prediction algorithm determines that a day in which operation hours of a virtual server are above a prescribed threshold (e.g., 30%) are a "business day” of the virtual server.
- a prescribed threshold e.g. 30%
- the load prediction algorithm determines that a particular hour of a day is "nonbusiness hours" when the number of days in which the particular hour of a day is operating hours from among business days in one month is below a threshold (e.g., 30%).
- this virtual server has nonbusiness hours from 2 a.m. to 6 a.m. and it can be predicted that this virtual server will not operate from 2 a.m. to 6 a.m. in the future.
- the load prediction algorithm determines that a particular hour of a day is "working hours" when the number of days in which the particular hour of a day is operating hours from among business days in one month is over a threshold (e.g., 30%).
- the load prediction algorithm it is preferable to execute a prediction method of the load value of the virtual server, as described below, involving only the business hours in the business days of the virtual server.
- FIG. 7 is a diagram that has an example of load values on an hourly basis added to FIG. 6 .
- the load values in the stopped time period of the virtual server, which is represented by gray, are all zero.
- the load prediction algorithm predicts load values sequentially in cycles having a duration of 168 hours (one week).
- the load values for one week are predicted by executing the moving average processing of the load values in each hour every week for the past several weeks, for example, using data of the past 10 weeks (load value data in a 168-hour cycle x 10).
- load value data in a 168-hour cycle x 10 load value data in a 168-hour cycle x 10.
- a value obtained by dividing the total value of the load values for seven hours that were operating hours by 7 is a load prediction value of the particular single hour.
- load values of every hour in future 168-hour periods (one week) are predicted every week.
- An example of prediction of load values of every hour for 168 hours (one week) is provided in FIG. 8 .
- the load prediction unit 24 obtains load data (load values and operation information) of the virtual servers Vx for ten weeks, for example (step S10), and analyzes the operation information of the obtained virtual servers Vx (step S12).
- the load prediction unit 24 can calculate the operation percentage of the virtual servers Vx of a particular time block of a day.
- the load prediction unit 24 determines that the particular time block is a stopped hour under the condition that the operation percentage is at a prescribed threshold or below, and determines that the particular time period is an operating hour under the condition that the operation percentage is at a prescribed threshold or above.
- the load prediction unit 24 generates prediction data of the operation status as illustrated in FIG. 6 (steps S14), for example.
- the load prediction unit 24 analyzes load values in the operation time period (operation hours on an hourly basis) (step S16). More specifically, the load prediction unit 24 averages the load value at one-minute intervals obtained in step S10 within each operation hour and calculates the load values in the operation hour. As a result, matrix data (e.g., data for ten weeks) illustrated in FIG. 7 as an example can be obtained.
- the load prediction unit 24 averages the load values of the operation hour for ten weeks and obtains the prediction load data during the operation hour (step S18).
- a value obtained by dividing the total of the load values for seven hours that are operation hours by 7 is the load prediction value of the particular single hour.
- the prediction load data includes information of stopped hours as well as the load prediction values.
- the prediction load data on a weekly basis is generated for all virtual servers.
- the optimal distribution creation unit 25 obtains the prediction load data of all virtual servers within each time block for one week in the future, for example, from the load prediction unit 24.
- the timing to obtain the prediction load data is not specifically limited, but the timing may be at intervals longer than the intervals of the sample timings of the load data (one minute in FIG. 3 ).
- the optimal distribution creation algorithm determines the schedule to distribute plural virtual servers to plural physical servers based on the load prediction values of each of the virtual servers so that the total of the load prediction values of one or plural virtual servers distributed to a physical server is within a prescribed range of proportion (acceptable range) with respect to the processing capacity of the physical server.
- the upper limit of the acceptable range is set to give a margin to tolerate an abrupt increase in the load of the virtual servers
- the lower limit of the acceptable range is set to reduce power consumption by utilizing the performance of the physical server without any waste and by minimizing the number of physical servers to be operated.
- an appropriate value of the prescribed proportion is set to 70%, and the upper limit of the acceptable range is set to 80%, and the lower limit is set to 60%.
- FIG. 10 illustrates an example of load prediction values of the virtual servers V1 to Vm and the processing capacity value of the physical servers P1 to Pn in a particular time block.
- the load prediction value and the processing capacity value illustrated in FIG. 10 are only an example for explanation, and these two values are index values that can be compared.
- the example assumes that the processing capacity value of each of the physical servers is 100, and the total of the load prediction values of plural virtual server to be distributed is 500. If the number of physical servers required for operating all of the virtual servers is N, then the smallest integer N where the inequation 100 x N x 70% ⁇ 500 is true is the minimum number of servers required. In this case, N ⁇ 7.14 is obtained and at least eight physical servers are required.
- the performance of all physical servers is assumed to be the same. However, when the performance is not the same, the left-hand side value may be a value that is a total of the physical server performance multiplied by 0.7.
- the optimal distribution creation algorithm allocates virtual servers to the eight physical servers (P 1 , P 2 , ..., P 8 ) in a descending order of the load prediction value. More specifically, the optimal distribution creation algorithm sequentially allocates the virtual servers in a manner of the first virtual server V 1 to the physical server P 1 , the second virtual server V 2 to the physical server P 2 , ..., the eighth virtual server V 8 to the physical server P 8 , the ninth virtual server V 9 to the physical server P 1 , ..., the sixteenth virtual server to the physical server P 8 .
- the virtual server is not allocated to this physical server, but is allocated to the next physical server. If the virtual server cannot be allocated to the next physical server, and cannot eventually be allocated to the eighth physical server P 8 , the ninth physical server P 9 is newly provided to allocate the virtual server. In this manner, the optimal distribution creation algorithm allocates all of the virtual servers and a distribution schedule is created in a particular time block.
- FIG. 11 is a flowchart of the processing of the optimal distribution creation unit 25
- FIG. 12 is a flowchart of the optimizing processing in FIG. 11 (a flowchart of the above-described optimal distribution creation algorithm).
- the optimal distribution creation unit 25 firstly, refers to the server control database 23 and obtains a list of physical servers and virtual servers (step S20). As a result, the virtual server ID of the virtual servers to be distributed and the processing capacity value of physical servers can be obtained (see FIG. 4 ). Next, the optimal distribution creation unit 25 obtains prediction load data (load prediction values, data of stopped hours) of all virtual servers within the time block Pt from the load prediction unit 24 (step S22). Since the load prediction value of all virtual servers to be distributed and the processing capacity values of the physical servers are obtained within the time block Pt as a result of steps S20 and S22, the optimizing processing is executed in accordance with the above-described optimal distribution creation algorithm (step S24).
- this optimizing processing is executed as below.
- steps S32 and S34 processing is performed to allocate each of the virtual servers sequentially to the physical server one by one.
- step S32 the judgment of whether the virtual server x can be distributed to the physical server y or not is based on whether the total of the load prediction values of the virtual servers distributed to the physical server is within a range of a prescribed proportion with respect to the processing capacity of the physical server or not.
- step S36 if no more virtual servers can be distributed to the physical servers 0 to n tmp , or in other words, if the range of the prescribed proportion (acceptable range) is not satisfied by the number of physical servers determined in step S30, under the condition that the physical server can be added (step S38), one physical server to be distributed is added (step S40), and the processing is continued.
- the explanation returns to the explanation of FIG. 11 .
- step S26 the combination of the optimal distribution in the time block Pt (combination of each physical server and vertical servers distributed to each physical server) is determined (step S26).
- steps S20 to S26 on all time blocks a distribution schedule on an hourly basis for one week in the future, for example, is created (step S28).
- An example of this distribution schedule is illustrated in FIG. 13 .
- the example of FIG. 13 represents that virtual servers V 1 , V 4 , V 7 , V 10 , and V 12 are distributed to the physical server P1 at a point in time 10:00:00 of the date YYYY/MM/DD, for example.
- the distribution schedule is stored in the distribution schedule data storage unit 28 as distribution schedule data.
- the processing executed by the redistribution execution unit 26 includes the following three types of processing (processing 6A, 6B, and 6C) of the time blocks to undergo redistribution (referred to as "target time block").
- the distribution schedule data of the target time block is loaded.
- a query on the server control database 23 about the information of the physical servers and the virtual servers is performed.
- the physical server operating in the target time block is compared with the physical server operating in the previous time block (one hour before) of the target time block. No particular processing is executed to the physical server that matches (i.e., a physical server operating in both of the time blocks), but an instruction to turn on or off the power is given to the physical server that does not match (i.e., a physical server operating in either one of the time blocks).
- the power is turned on prior to the distribution of the virtual servers in the target time block.
- the power disconnection of a physical server stopped during the target time block is carried out in a state in which the virtual servers distributed to the physical server are moved to another physical server and none of the virtual servers operates on the physical server.
- a physical server to which virtual servers are distributed in the target time block is compared with the same physical server in the previous time block.
- no processing is executed on the virtual servers distributed to the physical server that matches, but the virtual servers that do not match are given migration instructions.
- the comparison between the target time block and the previous time block of the target time block is performed by comparing the distribution schedule data loaded in the processing 6A.
- Another method of the comparison may include a method of obtaining information on the real-time operation status. The latter method makes it possible to take into account the unscheduled operation of a system administrator or the failure of the physical server.
- FIG. 14 and FIG. 15 illustrate an example of execution of redistribution.
- FIG. 14 assumes a case in which eight physical servers are in operation before the redistribution, as illustrated in (a). At that time, if it is found from the distribution schedule data that the schedule requires nine physical servers, the redistribution execution unit 26 instructs turning on of the power of another physical server before the redistribution as illustrated in (b). The reschedule execution unit 26 also instructs performing of migration of the virtual servers to the newly turned-on physical server as illustrated in (c).
- redistribution processing executed by the redistribution execution unit 26 to a particular time block (target time block) is explained with reference to the flowchart in FIG. 16 .
- the redistribution execution unit 26 reads out the distribution schedule data stored in the distribution schedule data storage unit 28, and loads a distribution list (data of a list of which physical server the virtual servers are distributed to) in the target time block from the distribution schedule data (step S50).
- the redistribution execution unit 26 performs a query about operation information (information indicating either an "operating" or "stopped” state) of the physical server and the virtual servers on the server control database 23 (step S52).
- the redistribution execution unit 26 compares the operation states of each of the physical servers in the target time block and the previous time block based on the operation information obtained in step S52, and finds out the change in the operation state of each physical server (step S54).
- the redistribution execution unit 26 compares the operation states of each of the virtual servers in the target time block and in the previous time block and finds out the change in the operation states of each of the virtual servers (step S56).
- the redistribution execution unit 26 when the number of the physical servers needs to be increased (YES in step S58) between the target time block and the previous time block, instructs the power of a newly added physical server to be turned on (step S60), but does nothing when the number of the physical servers does not need to be increased.
- the redistribution execution unit 26 instructs the virtual servers to be migrated in accordance with the distribution schedule data read out in step S50 (step S62).
- the redistribution execution unit 26 instructs power disconnection of the physical server to be decreased (step S66), but does nothing when the number of the physical servers does not need to be decreased.
- the redistribution processing is explained with reference to the flowchart. It is preferable for the execution of the redistribution to provide a scheduler to detect the time to start the processing of the target time block.
- This scheduler may be provided in the system control unit 21 or in the redistribution execution unit 26. When the scheduler is provided in the system control unit 21, an instruction to start the processing is issued to the redistribution execution unit 26 at the processing start time.
- the optimal distribution creation unit 25 preferably implements an algorithm to create a distribution schedule that takes into account reduction of this overhead to the minimum.
- the failure monitor unit 27 monitors the state (normal/failed) of each physical server, and rewrites the failure information of the record corresponding to the physical server on the server control database 23 to "failed" when a failure occurs (when a physical server is immediately stopped).
- the redistribution execution unit 26 performs automatic recovery by activating an alternative physical server and causing migration of the virtual servers in response to the change in the failure information of the physical server on the server control database 23.
- failure monitor unit 27 rewrite the failure information of the record corresponding to the physical server with the sign of failure to "failed" on the server control database 23.
- the physical server with the sign of failure is excluded from the physical server to be scheduled at the time of creating the next distribution schedule.
- the sign of failure here refers to events that are likely to lead to failure if it is left neglected, such as an abnormality in the number of rotations of the cooling fan in the server and correctable errors occurring more than a certain number of times in a given period of time.
- the failure monitor unit 27 rewrites the failure information of the corresponding physical server in the server control database 23 to "normal".
- the optimal distribution creation unit 25 the recovered physical server is incorporated into the physical servers to be scheduled at the time of creating the next distribution schedule.
- FIG. 17 is a flowchart illustrating processing of a case in which a failure or a sign of failure occurs in a physical server
- FIG. 18 is a flowchart illustrating processing of a case in which the physical server is recovered to the normal state by maintenance, replacement, or the like.
- the failure monitor unit 27 monitors each physical server to detect a failure/sign of failure of a physical server (step S70).
- the redistribution execution unit 26 issues an instruction to perform migration of all the virtual servers distributed to the failed physical server to an alternative physical server (step S74).
- step S74 is not executed.
- the failure monitor unit 27 rewrites the failure information of the physical server in which a failure or a sign of failure is detected to "failed" in the server control database 23 (step S76).
- the optimal distribution creation unit 25 excludes the physical server in which a failure or a sign of failure is detected from candidates of operating physical servers that are physical server candidates to be scheduled at the time of creating the next distribution schedule.
- the failure monitor unit 27 monitors each physical server to detect recovery of the physical server (step S80).
- the failure monitor unit 27 rewrites the failure information of the physical server from which the recovery is detected to "normal" in the server control database 23 (step S82).
- the optimal distribution creation unit 25 incorporates the recovered physical server into candidates of the physical server to be scheduled at the time of creating the next distribution schedule.
- the above-described optimal distribution creation algorithm processing of the optimal distribution creation unit 25 is explained using a case in which a distribution schedule for one week in the future is created in advance.
- a schedule is recreated excluding the physical server in which the failure or the sign of failure occurred in the subsequent time blocks.
- the recreation of the schedule can be skipped by replacing the physical server in which a failure or a sign of failure occurred with this physical server.
- Methods of failure detection (recovery) in physical servers performed by the failure monitor unit 27 are not limited in particular, but possible methods include, for example, a method in which events from monitor software provided from a vendor of the physical servers is used as a trigger, a method in which the failure monitor unit 27 collects information relating to the state of physical servers through communications with each physical server, and a method in which information relating to the state of physical servers is obtained and updated from input operations of an operator.
- a load prediction value is calculated from the past load data of each of plural virtual servers, an optimal distribution schedule of the virtual servers to a physical server is created, and redistribution is periodically executed.
- the total of the load values predicted from plural virtual servers distributed on a particular physical server is within a range of appropriate proportion with respect to the processing capacity value of the particular physical server.
- control server according to embodiments of the present invention is not limited to the above embodiments, but it is obviously possible to make various improvements and modifications within a scope that does not depart from the gist of the present invention.
- the future load values of each virtual server are predicted on the basis of the load values of each of plural virtual servers in a prescribed time period up to the present
- a schedule to distribute the plural virtual servers to plural physical servers is determined based on the load prediction values of each virtual server so that the total of the load prediction value of one or plural virtual servers distributed in a physical server is within a prescribed range of proportion with respect to the processing capacity of the physical server, and an instruction is issued to distribute a portion or all of the plural virtual servers to a portion or all of plural physical servers in accordance with the schedule.
- each of the components of the control server according to the above embodiments or the above virtual server distribution method can be realized by programs.
- a microcontroller (computer) included in the system control unit 21, for example to execute a server control program in which procedures of the above virtual server distribution method are written
- the above-described virtual server distribution method is realized by using hardware resources of each of the components including the load prediction unit 24, the optimal distribution creation unit 25, the distribution schedule data storage unit 28, and the redistribution execution unit 26.
- the above program may be incorporated in advance into the control server as firmware or may be executed by the control server as versatile software.
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
- Power Sources (AREA)
- Computer And Data Communications (AREA)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2009/002421 WO2010140183A1 (ja) | 2009-06-01 | 2009-06-01 | サーバ管理プログラム、管理サーバ、仮想サーバ配置方法 |
Publications (3)
Publication Number | Publication Date |
---|---|
EP2439641A1 EP2439641A1 (en) | 2012-04-11 |
EP2439641A4 EP2439641A4 (en) | 2013-05-01 |
EP2439641B1 true EP2439641B1 (en) | 2016-10-12 |
Family
ID=43297332
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP09845469.7A Not-in-force EP2439641B1 (en) | 2009-06-01 | 2009-06-01 | Server control program, control server, virtual server distribution method |
Country Status (6)
Country | Link |
---|---|
US (1) | US8782652B2 (ja) |
EP (1) | EP2439641B1 (ja) |
JP (1) | JP5338906B2 (ja) |
KR (1) | KR101351688B1 (ja) |
CN (1) | CN102449603B (ja) |
WO (1) | WO2010140183A1 (ja) |
Families Citing this family (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011118424A1 (ja) * | 2010-03-25 | 2011-09-29 | 日本電気株式会社 | マシン稼動計画作成装置、マシン稼動計画作成方法、及びマシン稼動計画作成用プログラム |
US8782211B1 (en) * | 2010-12-21 | 2014-07-15 | Juniper Networks, Inc. | Dynamically scheduling tasks to manage system load |
JP5257709B2 (ja) * | 2010-12-28 | 2013-08-07 | 株式会社日立製作所 | 仮想計算機の移動方法、仮想計算機システム及び管理サーバ |
JP5708013B2 (ja) * | 2011-02-22 | 2015-04-30 | 富士通株式会社 | 仮想マシンの配置変更方法、仮想マシンの配置変更装置、及び、仮想マシンの配置変更プログラム |
JP5412599B2 (ja) * | 2011-03-03 | 2014-02-12 | 株式会社日立製作所 | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 |
JP5664376B2 (ja) * | 2011-03-17 | 2015-02-04 | 日本電気株式会社 | 仮想計算機割り当てシステム、及び仮想計算機割り当て方法 |
JP5576827B2 (ja) * | 2011-06-03 | 2014-08-20 | 日本電信電話株式会社 | サーバ管理システム、サーバ管理装置、サーバ管理方法、及びサーバ管理プログラム |
TW201305824A (zh) * | 2011-07-21 | 2013-02-01 | Hon Hai Prec Ind Co Ltd | 電源管理系統及方法 |
US9183102B2 (en) | 2011-09-30 | 2015-11-10 | Alcatel Lucent | Hardware consumption architecture |
WO2013051136A1 (ja) * | 2011-10-06 | 2013-04-11 | 株式会社日立製作所 | 仮想サーバ処理制御方法、システムおよび仮想サーバ処理制御管理サーバ |
JP5722247B2 (ja) * | 2012-02-10 | 2015-05-20 | 株式会社野村総合研究所 | 仮想サーバ管理システム |
CN103368785A (zh) * | 2012-04-09 | 2013-10-23 | 鸿富锦精密工业(深圳)有限公司 | 服务器运行监测***及方法 |
CN103827827B (zh) * | 2012-09-21 | 2017-05-17 | 株式会社东芝 | ***管理装置、网络***以及***管理方法 |
US9104607B2 (en) * | 2012-10-31 | 2015-08-11 | International Business Machines Corporation | Simulation engine for use in disaster recovery virtualization |
EP2755135B1 (en) * | 2013-01-14 | 2016-07-13 | Fujitsu Limited | Computing device, method, and program for energy-efficient distribution of computational load |
JP2014142678A (ja) * | 2013-01-22 | 2014-08-07 | Hitachi Ltd | 仮想サーバ移行計画作成方法およびシステム |
WO2014192132A1 (ja) * | 2013-05-31 | 2014-12-04 | 株式会社日立製作所 | 負荷分散装置及び方法 |
JP6264102B2 (ja) * | 2014-03-07 | 2018-01-24 | 富士通株式会社 | 情報処理プログラム、情報処理方法、及び情報処理装置 |
JP6263083B2 (ja) * | 2014-05-13 | 2018-01-17 | 日本電信電話株式会社 | 仮想システムの稼働率管理方法、稼働率管理プログラム、および稼働率管理装置 |
JP6455035B2 (ja) | 2014-09-10 | 2019-01-23 | 富士通株式会社 | 負荷分散管理装置、制御方法およびプログラム |
JP6259388B2 (ja) * | 2014-12-03 | 2018-01-10 | 日本電信電話株式会社 | 電源制御装置、サーバ仮想化システム、および、電源制御方法 |
JP5857144B2 (ja) * | 2015-03-04 | 2016-02-10 | 株式会社野村総合研究所 | 仮想サーバ管理システム |
JP6426532B2 (ja) * | 2015-05-08 | 2018-11-21 | 株式会社日立製作所 | 仮想マシン運用支援システムおよび仮想マシン運用支援方法 |
KR102607808B1 (ko) * | 2015-09-11 | 2023-11-30 | 삼성전자주식회사 | 분산 이종 컴퓨터 시스템에서의 최적화된 잡 성능을 위한 동적 자원 재할당 |
JP6640025B2 (ja) * | 2016-05-27 | 2020-02-05 | 本田技研工業株式会社 | 分散処理制御システム及び分散処理制御方法 |
JP6571046B2 (ja) * | 2016-06-21 | 2019-09-04 | 株式会社東芝 | サーバ装置、情報処理方法及びプログラム |
WO2018152386A1 (en) * | 2017-02-16 | 2018-08-23 | Casa Systems, Inc. | Scalable evolved packet core |
JP6891611B2 (ja) | 2017-04-17 | 2021-06-18 | 富士通株式会社 | 管理装置、情報処理システムの制御方法、および管理装置の管理プログラム |
US10594216B2 (en) | 2018-03-23 | 2020-03-17 | Dell Products, L.P. | Configurable voltage drop compensation method and apparatus for voltage regulators |
CN108881435B (zh) * | 2018-06-15 | 2021-12-03 | 广东美的制冷设备有限公司 | 实时时钟提供方法、服务器、家电设备、***和介质 |
JP7035858B2 (ja) | 2018-07-03 | 2022-03-15 | 富士通株式会社 | マイグレーション管理プログラム、マイグレーション方法およびマイグレーションシステム |
JP2020038434A (ja) * | 2018-09-03 | 2020-03-12 | 日本電信電話株式会社 | リソース割当装置、リソース割当方法およびリソース割当プログラム |
JP7197776B2 (ja) * | 2018-11-01 | 2022-12-28 | 富士通株式会社 | スケジューリングプログラム、スケジューリング方法、およびスケジューリング装置 |
KR102062157B1 (ko) | 2019-04-29 | 2020-01-03 | 오케스트로 주식회사 | 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
KR102135209B1 (ko) * | 2019-08-19 | 2020-07-17 | 오케스트로 주식회사 | 가상 머신 배치 모의 실험 방법 및 이를 구현하는 가상 머신 배치 모의 실험 장치 |
KR102135208B1 (ko) * | 2019-07-31 | 2020-07-17 | 오케스트로 주식회사 | 스케줄링을 통한 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
KR102316749B1 (ko) * | 2019-07-31 | 2021-10-25 | 오케스트로 주식회사 | 가상 머신 워크로드 예측 방법, 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
KR102347371B1 (ko) * | 2019-08-19 | 2022-01-05 | 오케스트로 주식회사 | 딥러닝을 이용한 가상 머신 배치 시뮬레이션 방법 및 이를 실행하는 가상 머신 배치 모의 실험 장치 |
KR102284074B1 (ko) * | 2019-12-26 | 2021-07-30 | 연세대학교 산학협력단 | 가상머신 워크로드 클러스터링 예측을 활용한 높은 전력 효율성을 제공하는 다중 서버 관리 방법 |
KR102126434B1 (ko) * | 2019-12-27 | 2020-06-25 | 오케스트로 주식회사 | 딥 러닝을 활용한 워크 로드 예측을 통한 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
JP7261195B2 (ja) * | 2020-03-25 | 2023-04-19 | 株式会社日立製作所 | サーバ負荷予測システム及びサーバ負荷予測方法 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050060590A1 (en) * | 2003-09-16 | 2005-03-17 | International Business Machines Corporation | Power-aware workload balancing usig virtual machines |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003271572A (ja) | 2002-03-14 | 2003-09-26 | Fuji Photo Film Co Ltd | 処理分散制御装置、分散処理システム、処理分散制御プログラム、処理分散制御方法 |
US8776050B2 (en) * | 2003-08-20 | 2014-07-08 | Oracle International Corporation | Distributed virtual machine monitor for managing multiple virtual resources across multiple physical nodes |
US7689685B2 (en) * | 2003-09-26 | 2010-03-30 | International Business Machines Corporation | Autonomic monitoring for web high availability |
JP3861087B2 (ja) | 2003-10-08 | 2006-12-20 | 株式会社エヌ・ティ・ティ・データ | 仮想マシン管理装置及びプログラム |
US7437730B2 (en) * | 2003-11-14 | 2008-10-14 | International Business Machines Corporation | System and method for providing a scalable on demand hosting system |
JP2006172241A (ja) | 2004-12-17 | 2006-06-29 | Fujitsu Ltd | 負荷分散装置,負荷分散方法および負荷分散プログラム |
US7730486B2 (en) | 2005-02-28 | 2010-06-01 | Hewlett-Packard Development Company, L.P. | System and method for migrating virtual machines on cluster systems |
WO2008102739A1 (ja) * | 2007-02-23 | 2008-08-28 | Nec Corporation | 仮想サーバシステム及び物理サーバ選択方法 |
JP4875525B2 (ja) * | 2007-03-26 | 2012-02-15 | 株式会社日立製作所 | 仮想計算機システム及びプログラム |
JP2008276320A (ja) * | 2007-04-25 | 2008-11-13 | Nec Corp | 仮想システム制御方法およびコンピュータシステム |
US20100250734A1 (en) * | 2007-09-18 | 2010-09-30 | Nec Corporation | Server reassignment support system and server reassignment support method |
US8468230B2 (en) | 2007-10-18 | 2013-06-18 | Fujitsu Limited | Method, apparatus and recording medium for migrating a virtual machine |
JP5104588B2 (ja) * | 2007-10-18 | 2012-12-19 | 富士通株式会社 | マイグレーションプログラム、および仮想マシン管理装置 |
JP5000456B2 (ja) * | 2007-10-31 | 2012-08-15 | ヒューレット−パッカード デベロップメント カンパニー エル.ピー. | 資源管理システム、資源管理装置およびその方法 |
JP5378946B2 (ja) | 2009-10-26 | 2013-12-25 | 株式会社日立製作所 | サーバ管理装置およびサーバ管理方法 |
-
2009
- 2009-06-01 JP JP2011518062A patent/JP5338906B2/ja active Active
- 2009-06-01 WO PCT/JP2009/002421 patent/WO2010140183A1/ja active Application Filing
- 2009-06-01 EP EP09845469.7A patent/EP2439641B1/en not_active Not-in-force
- 2009-06-01 KR KR1020117028077A patent/KR101351688B1/ko not_active IP Right Cessation
- 2009-06-01 CN CN200980159500.7A patent/CN102449603B/zh not_active Expired - Fee Related
-
2011
- 2011-11-16 US US13/297,840 patent/US8782652B2/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050060590A1 (en) * | 2003-09-16 | 2005-03-17 | International Business Machines Corporation | Power-aware workload balancing usig virtual machines |
Also Published As
Publication number | Publication date |
---|---|
JP5338906B2 (ja) | 2013-11-13 |
JPWO2010140183A1 (ja) | 2012-11-15 |
US20120066684A1 (en) | 2012-03-15 |
KR101351688B1 (ko) | 2014-01-14 |
EP2439641A4 (en) | 2013-05-01 |
CN102449603B (zh) | 2014-10-08 |
WO2010140183A1 (ja) | 2010-12-09 |
US8782652B2 (en) | 2014-07-15 |
KR20120023703A (ko) | 2012-03-13 |
EP2439641A1 (en) | 2012-04-11 |
CN102449603A (zh) | 2012-05-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2439641B1 (en) | Server control program, control server, virtual server distribution method | |
EP3847549B1 (en) | Minimizing impact of migrating virtual services | |
US10904159B2 (en) | Resource allocation optimizing system and method | |
US8291414B2 (en) | Shared resource service provisioning using a virtual machine manager | |
US8191069B2 (en) | Method of monitoring performance of virtual computer and apparatus using the method | |
US8214843B2 (en) | Framework for distribution of computer workloads based on real-time energy costs | |
US20120005683A1 (en) | Data Processing Workload Control | |
EP2391961B1 (en) | System and method for integrating capacity planning and workload management | |
US9128766B1 (en) | Computer workload redistribution schedule | |
WO2012066604A1 (en) | Server system and method for managing the same | |
US7849347B2 (en) | System and method for updating a time-related state of a migrating logical partition | |
US20080184241A1 (en) | Techniques for automated balancing of tasks across multiple computers | |
US20120324200A1 (en) | Method and apparatus of memory overload control | |
US20080091748A1 (en) | Storage capacity management system in dynamic area provisioning storage | |
US20080133741A1 (en) | Computer program and apparatus for controlling computing resources, and distributed processing system | |
US8024542B1 (en) | Allocating background workflows in a data storage system using historical data | |
KR20190066516A (ko) | 도커 컨테이너 관리 시스템 및 방법, 이를 수행하기 위한 기록매체 | |
JP5664339B2 (ja) | 情報処理装置、仮想マシン管理方法および仮想マシン管理プログラム | |
US20110231686A1 (en) | Management apparatus and management method | |
US11748125B2 (en) | Systems and methods of auto-scaling a virtual desktop environment | |
JP2011253475A (ja) | 計算機システム | |
US20230089581A1 (en) | Systems and methods of auto-scaling a virtual desktop environment | |
CN103189850A (zh) | 将附加的存储空间供应至计算机应用程序的方法 | |
US20230096984A1 (en) | Systems and methods of auto-scaling a virtual desktop environment | |
US20240256310A1 (en) | Systems and methods of auto-scaling a virtual desktop environment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20111223 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK TR |
|
DAX | Request for extension of the european patent (deleted) | ||
A4 | Supplementary search report drawn up and despatched |
Effective date: 20130403 |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06F 9/50 20060101AFI20130326BHEP Ipc: G06F 9/46 20060101ALI20130326BHEP |
|
17Q | First examination report despatched |
Effective date: 20140113 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20160504 |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: TAKAMI, HIROYUKI |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 837083 Country of ref document: AT Kind code of ref document: T Effective date: 20161015 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602009041762 Country of ref document: DE |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: MP Effective date: 20161012 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 837083 Country of ref document: AT Kind code of ref document: T Effective date: 20161012 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 9 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170113 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170112 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: BE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170213 Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170212 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 602009041762 Country of ref document: DE |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20170419 Year of fee payment: 9 Ref country code: GB Payment date: 20170403 Year of fee payment: 9 Ref country code: DE Payment date: 20170227 Year of fee payment: 9 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20170112 |
|
26N | No opposition filed |
Effective date: 20170713 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: MM4A |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170630 Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170601 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170630 Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170601 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20170601 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 602009041762 Country of ref document: DE |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20180601 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180601 Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20190101 Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20180630 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20090601 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20161012 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20161012 |